论文标题
需要零经验：插件和播放模块化转移学习用于语义视觉导航
Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation
论文作者
论文摘要
在视觉导航的强化学习中，通常是为每个新任务开发一个模型，并通过3D环境中特定于任务的交互从头开始训练该模型。但是，这个过程很昂贵。该模型需要大量的相互作用才能很好地概括。此外，只要任务类型或目标模式发生变化，就会重复此过程。我们使用新型的模块化传输学习模型提出了一种统一的视觉导航方法。我们的模型可以有效地利用其经验从一个源任务中，并将其应用于具有各种目标模态（例如，图像，素描，音频，标签）的多个目标任务（例如ObjectNav，RoomNav，ViewNav）。此外，我们的模型可以使零射击体验学习，从而可以解决目标任务，而无需接受任何特定任务的互动培训。我们在多个逼真的数据集和具有挑战性的任务上进行的实验表明，我们的方法可以更快地学习，更好地概括，并以显着的差距超过SOTA模型。
In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environments. However, this process is expensive; massive amounts of interactions are needed for the model to generalize well. Moreover, this process is repeated whenever there is a change in the task type or the goal modality. We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks (e.g., ObjectNav, RoomNav, ViewNav) with various goal modalities (e.g., image, sketch, audio, label). Furthermore, our model enables zero-shot experience learning, whereby it can solve the target tasks without receiving any task-specific interactive training. Our experiments on multiple photorealistic datasets and challenging tasks show that our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
